Content Planning for Neural Story Generation with Aristotelian Rescoring
This addresses the issue of structural incoherence in neural story generation for applications like creative writing or entertainment, though it is incremental as it builds on existing planning methods.
The paper tackles the problem of generating globally coherent long-form narratives by proposing a content planning system that uses a plot-generation language model and Aristotelian rescoring models, resulting in stories that are more relevant and higher quality than baselines without principled planning.
Long-form narrative text generated from large language models manages a fluent impersonation of human writing, but only at the local sentence level, and lacks structure or global cohesion. We posit that many of the problems of story generation can be addressed via high-quality content planning, and present a system that focuses on how to learn good plot structures to guide story generation. We utilize a plot-generation language model along with an ensemble of rescoring models that each implement an aspect of good story-writing as detailed in Aristotle's Poetics. We find that stories written with our more principled plot-structure are both more relevant to a given prompt and higher quality than baselines that do not content plan, or that plan in an unprincipled way.